Content-based image retrieval speedup

TL;DR

This paper introduces a novel CBIR speedup method that uses Zernike moments to reduce the database size by filtering irrelevant images, thereby accelerating retrieval without sacrificing accuracy.

Contribution

The paper proposes a new database reduction technique based on Zernike moments that maintains retrieval accuracy while significantly improving speed.

Findings

Retrieval speed increased by reducing database size

Relevant images are preserved after filtering

Accuracy of CBIR remains high despite acceleration

Abstract

Content-based image retrieval (CBIR) is a task of retrieving images from their contents. Since retrieval process is a time-consuming task in large image databases, acceleration methods can be very useful. This paper presents a novel method to speed up CBIR systems. In the proposed method, first Zernike moments are extracted from query image and an interval is calculated for that query. Images in database which are out of the interval are ignored in retrieval process. Therefore, a database reduction occurs before retrieval which leads to speed up. It is shown that in reduced database, relevant images to query image are preserved and irrelevant images are throwed away. Therefore, the proposed method speed up retrieval process and preserve CBIR accuracy, simultaneously.